日本語フィールド
著者：Tanaka, Yuya; Minamoto, Teruya題名：Detection of Early Gastric Cancer from Endoscopic Images Using Wavelet Transform Modulus Maxima発表情報：Advances in Intelligent Systems and Computing 巻: 738 ページ: 589 - 594キーワード：概要：© 2018, Springer International Publishing AG, part of Springer Nature. It is said that the overlooking rate of early gastric cancer in endoscopic examination reaches 20–25% in Japan, and it is desirable to develop a detection method for early gastric cancer from endoscopic images to reduce the overlooking rate. We propose a new method for detecting early gastric cancer from endoscopic images using the wavelet transform modulus maxima (WTMM). First, our method converts the original image into the CIE L*a*b* color space. Next, we apply the dyadic wavelet transform (DYWT) to the a* component image and compute the WTMM of the high frequency component. It is shown that the WTMM of the abnormal parts tends to become smaller than the WTMM of the normal parts. We describe the method detecting the abnormal parts based on these features in detail, we show experimental results demonstrating that the proposed method are able to detect the regions suspected of being early gastric cancer from endoscopic images.抄録：英語フィールド
Author：Tanaka, Yuya; Minamoto, TeruyaTitle：Detection of Early Gastric Cancer from Endoscopic Images Using Wavelet Transform Modulus MaximaAnnouncement information:Advances in Intelligent Systems and Computing Vol: 738 Page: 589 - 594An abstract：© 2018, Springer International Publishing AG, part of Springer Nature. It is said that the overlooking rate of early gastric cancer in endoscopic examination reaches 20–25% in Japan, and it is desirable to develop a detection method for early gastric cancer from endoscopic images to reduce the overlooking rate. We propose a new method for detecting early gastric cancer from endoscopic images using the wavelet transform modulus maxima (WTMM). First, our method converts the original image into the CIE L*a*b* color space. Next, we apply the dyadic wavelet transform (DYWT) to the a* component image and compute the WTMM of the high frequency component. It is shown that the WTMM of the abnormal parts tends to become smaller than the WTMM of the normal parts. We describe the method detecting the abnormal parts based on these features in detail, we show experimental results demonstrating that the proposed method are able to detect the regions suspected of being early gastric cancer from endoscopic images.